条件熵正则化的 Evidential Deep Learning 用于青光眼检测

在 EyePACS-AIROGS-light-V2 和 RIM-ONE-DL 两个数据集上验证，该模型的不确定性估计校准误差显著低于 Deep Ensembles、MC Dropout、事后校准以及基于 Dempster 不确定性的常规 EDL。

可解释性方面，研究用 Grad-CAM 热力图的聚焦指数分析空间集中度，EDL 模型在分类正确与错误样本的指数分布上分离更明显。假阴性样本的 Grad-CAM 激活集中于偏离视盘的位置，而视盘正是青光眼临床评估的关键区域。

Evidential Deep Learning with conditional entropy for glaucoma detection

We propose a novel conditional entropy function as a basis for quantifying predictive uncertainty in Evidential Deep Learning (EDL) for glaucoma detection from retinal fundus images. Using the EyePACS-AIROGS-light-V2 and RIM-ONE-DL datasets for validation, we found that our proposed EDL model regularized by conditional entropy function produced uncertainty estimates with substantially lower calibration errors than Deep Ensembles, MC Dropout, post-hoc calibration and the conventional EDL framework based on Dempster uncertainty. To further probe our models' interpretability, we analyzed Grad-CAM heatmaps using a focus index representing spatial concentration. Compared with the other uncertainty quantification methods, EDL models exhibited greater separation between the index distributions of correctly and incorrectly classified fundus images. In particular, false negatives were associated with localized Grad-CAM activations that were displaced from the optic disc, consistent with its established clinical importance in glaucoma assessment. Overall, our findings suggest that our proposed EDL framework for glaucoma detection provides not only enhanced uncertainty calibration but also admits a more physiologically consistent interpretability.

This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include Evidential Deep Learning, 青光眼检测, 不确定性量化, Grad-CAM.

Source attribution: curated from arXiv cs.LG (@Hai Siong Tan, Kuancheng Wang).